get_content

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses return types for each output_format, explains the effect of include_shadow_dom (including when it is ignored), and reveals URL discovery behavior (including resource types and URL prefixing). This goes beyond a simple 'read' and details operational traits an agent needs to anticipate results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence is purposeful. It is structured into clear sections (Args, Returns, Tool selection) and front-loads the core purpose. The multiple paragraphs are justified by the tool's complexity (three parameters, three output modes, shadow DOM handling). There is no redundant phrasing or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's richness (three parameters, three return types, shadow DOM nuance, and a large sibling set), the description covers all essential aspects: parameter behavior, return formats, and usage disambiguation. The presence of an output schema is complemented by the description's explicit return type explanations, leaving no critical gap for an agent to resolve correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has zero descriptions (coverage 0%), so the description must fully compensate. It does: selector is explained as an optional scoping mechanism for all formats, output_format is elaborated with concrete meaning for each enum value, and include_shadow_dom is clarified with conditions. This adds substantial semantic value beyond the schema's bare type definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear statement of the tool's function: 'Read visible text, HTML, or discovered URLs from the current page.' This identifies the specific verb (read), resource (current page), and output formats. It distinguishes itself from siblings via a dedicated 'Tool selection' section that lists alternatives for metadata (get_page_info), structure (find_elements), presence checks (check_for_condition), and waits (wait_for).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use the tool ('Use this tool when you need actual page content or URL information rather than page metadata') and provides a comprehensive 'Tool selection' section that maps needs to specific sibling tools (e.g., 'Need URL, title, origin, or User-Agent -> use get_page_info'). This gives explicit when/when-not guidance without leaving inference to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.